Read docs pages
get_docsRead AI-written documentation pages for a tracked project, including area facts, current wording, and changes since each snapshot, to decide what to update before writing with write_docs.
Instructions
Read the docs pages ShadowGit keeps for a tracked project: one per area of its map, plus an Overview, each written by an AI assistant. A page comes with the facts ShadowGit draws from the map (folder, sizes, layers, what it depends on and what depends on it, processes, its most depended-on symbols, the project's rules that name it), its words so far with who wrote them and at which snapshot, and what changed in the area since them: symbols changed in their code, dependency facts, links that no longer name anything. With no arguments: the pages the latest AI session changed whose words are missing or behind. With areas, and overview: those pages. With all: pages without words, largest area first, five at a time, with more for the following batch. Answers head, the snapshot write_docs keeps the words at, and next: write the pages' words with write_docs. Needs the ShadowGit app running.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| all | No | Pages without words, five at a time | |
| more | No | The more get_docs answered with all, as given: the following batch | |
| repo | No | Project name or absolute path. Defaults to the current project. | |
| areas | No | Area ids, as get_docs names them: most are the area's folder, as get_map lists it | |
| overview | No | The Overview page, alone or with areas |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| head | Yes | The newest snapshot, which write_docs keeps the words at | |
| more | Yes | For all: the following batch, to pass back as more; null at the last | |
| next | No | The step that follows: write these pages with write_docs | |
| repo | Yes | ||
| pages | Yes | ||
| limits | Yes | ||
| mapAsOf | Yes | The snapshot the answer is drawn from |